WO2011141586A1 - Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications - Google Patents
Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications Download PDFInfo
- Publication number
- WO2011141586A1 WO2011141586A1 PCT/ES2010/070324 ES2010070324W WO2011141586A1 WO 2011141586 A1 WO2011141586 A1 WO 2011141586A1 ES 2010070324 W ES2010070324 W ES 2010070324W WO 2011141586 A1 WO2011141586 A1 WO 2011141586A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- quality
- experience
- user
- services
- perception
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5061—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the interaction between service providers and their network customers, e.g. customer relationship management
- H04L41/5067—Customer-centric QoS measurements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/80—Responding to QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2227—Quality of service monitoring
Definitions
- the present invention refers to a method for calculating the perception of user experience of the quality of the monitored services integrated in telecommunications operators.
- the main field of application is innovation in monitoring services in telecommunications operators.
- the present invention comprises a method that proposes to use data from the monitoring of the services used by the users together with questionnaires previously filled out by a representative sample of users for later mixing by means of correlation algorithms and after being passed through algorithms of Automatic learning to obtain from them a value of the quality of the experience that supposes an estimate of the quality of the service perceived by the user who makes use of said service.
- POTS Old Ordinary Telephone Service
- MOS Mean Opinion Score
- the average opinion score is a numerical figure that estimates the perceived quality of a conversation service, expressed within a whole range of 1 to 5, where 1 is the lowest perceived quality, and 5 is the Higher perceived quality.
- MOS tests for voice are specified in ITU-T Recommendation P.800 "Methods for subjective determination of transmission quality".
- PESQ Voice Quality Perception Assessment
- PSQM Voice Quality Perception Measurement
- PESQ voice quality perception
- the original (reference) signal is compared with the received (degraded) signal and a PESQ score is calculated as a prediction of the subjective quality of each test pulse, which is performed using active probes.
- PEVQ Advanced Video Quality Perception Assessment
- ITU-T Recommendation P.563 defines a "Unique method of objective evaluation of high quality voice in narrowband telephony applications". However, the method is based on knowledge about human language, so it is not necessary to use real users as input. The results are not very accurate because they must be used together with PESQ.
- Quality of user experience mainly includes the calculation of MOS from intrusive models (PESQ for VoIP, PEVQ for video) that They take into account user opinions only when it is defined by the model and is the only one involved. This may be valid for stable services such as VoIP in PESQ, but it is not valid for strongly dependent content services such as IPTV or MobileTV.
- Opinion polls are not part of current models, so there is no temporary comparison with network or business indicators.
- the models that calculate the MOS with user perception are based on intrusive tests, using the corresponding QoE measurement platform based on active probes. Some alternatives may use non-intrusively data sources, but they cannot be considered as QoE measurement platforms but service quality measurement (QoS) platforms.
- QoS service quality measurement
- the characteristics of each session are collected in a specific detailed record (XDR or IPDR for IP networks), which contains the essential data for quality purposes.
- the data sources of these procedures are the protocol data units, usually obtained from the passive probes installed in the monitoring network.
- XDR Generic Detailed Registration
- a user service containing network, service and user data is reconstructed, in terms of the quality of the experience
- Some models such as P.563 calculate the quality figures in a passive manner only for conversation services, without taking into account the validation of the users in the model, so they cannot be considered as real QoE monitoring solutions. This means that the procedures cannot be used to handle a large amount of data if it is used with the traffic of real users.
- XDRs include the information of any user when using any service, but only from the network and service perspective since the data sources are only telecommunications systems, and does not involve the user in any way.
- the present invention describes a method for calculating the customer's perception of user experience within a telecommunications operator, such as voice, video, multimedia data, etc., which is based on different data profiles (passive monitoring of real user data and surveys to optimize accuracy) and that includes the correlation of both data profiles to give a single final perspective of customer perception.
- This method is supported by a network monitoring system.
- the questionnaires of the levels of quality perceived by the client will be used to adjust the QoE, by establishing a series of limits and thresholds that are applied in the monitoring indicators in order to establish some benchmarks in terms of perception.
- the input data of the input network consists of a set of indicators for each service used, they are collected by passive probes deployed throughout the monitoring network (for example, XDR). This data provides a real view of the service of any user, since all of them are permanently monitored.
- These indicators include a wide variety of parameters of the multimedia coding domain, transport, as well as the terminal in which the media are presented and, finally, the type of content that the user is experiencing.
- This QoE approach analyzes the correlation of all these parameters to maximize user experience and minimize provider resources.
- the procedure generates a QoE value that can be named as an estimated experience score, for any user when using a service, which shows the satisfaction perceived when using the service by the end user.
- This QoE value will also be included in the XDR, in order to be part of the monitoring information.
- the present invention has the following advantages over known solutions:
- This invention can predict how each customer receives the services they use, without asking about their experience.
- the input information is extracted exclusively from the monitored network systems already deployed.
- the methodology object of the invention allows an accurate prediction of the values of the QOS MOS starting from small subjective initial studies in real-time environments. This is done through an innovative approach to the use of automatic learning algorithms for the construction of prediction models in the data from subjective studies.
- the solution can provide a realistic view of a service used by any user based on a single indicator (MOS), its accuracy and the attributes of the quality of service that have contributed to the perception that customers have of said service. service.
- MOS single indicator
- this method can be applied to a network operator or service provider to have a reliable tool to know what the customer opinion of any service is. Therefore, this method allows a realistic approach to QoE monitoring, which can be used for different purposes, such as service planning, marketing campaigns and more precise management of business relationships with customers.
- the present invention consists on the one hand of a method for calculating the perception of user experience of the quality of the monitored services integrated in telecommunications operators, any type of service being able to be monitored.
- This procedure includes at least as input data, network data obtained through monitoring platforms previously deployed in network operators of the services used by some users and experience questionnaires related to a service used that have been previously filled in by a set of users, characterized in that it comprises the following phases: i) mix, for each question of the experience questionnaire, the network data together with the answers to that question using conventional correlation algorithms;
- iv) combine the prediction models generated in the previous phase through a weighted voting system generating a single final prediction model; and, v) generate an MOS experience quality value for each network data through a platform for predicting the quality of experience in which the prediction model generated in phase iv) is integrated.
- the correlation algorithms of the phase of mixing the network data, phase i) identify the network data and the data of the questionnaires that are mixed by means of a unique identification key of the user identifier fields comprising a number telephone number of the user who has filled in the questionnaire and an IP address assigned to said user of the identifier of the content served where the type of content and time stamp of the service is specified, which includes the moment in which the service was used.
- the training data that is stored in phase ii) contains the most significant parameters that they contribute to the quality of experience being said parameters selected, when it comes to services offered over IP networks, among, type of content, result of the service, user agent, sequence losses, assent losses, packet loss rate, percentage of packet loss, burst packet loss, maximum, minimum and average performance values, delay and delay variance and a combination thereof.
- the aforementioned network data that are monitored to be used as input of the invention comprise information about services on IP networks offered by telecommunications operators selected from Television on IP (IPTV, TVoDSL, HDTVoIP, IPMS based on IMS, TV on FTTH, TV on GPON, TV on WiMax, mobile TV, 3G TV, 4G TV, videostreaming, Internet TV, IPTV-DTH) and its subservices (video on demand, pay per view, multicast TV, general broadcast TV, broadband multicast hybrid (HbbTV), P2PTV), Telephony over IP (VoIP, VoIP, telephone over Internet, voice over broadband (VoBB), VoIP based on IMS, ToIP, videotelephony over IP, conference call over IP) and its subservices (voice, data , instant messaging, presence, registration), Internet services (web browsing, email, file hosting, videostreaming, XML transactions) and particular services of telecommunications operators (Mensa jer ⁇ a, MMS, SMS, signaling, SS7, roaming,
- the training record generated in phase iii) comprises the most significant parameters to contribute to the calculation of the user experience, said parameters being selected, when it comes of services offered over IP networks, among, type of content, result of the service, user agent, sequence losses, loss of assent, lost packet rate, percentage of packet loss, burst packet loss, maximum, minimum values and means of performance, delay and variance of the delay and a combination thereof.
- the automatic learning algorithm of this phase automatically selects the parameters based on their relevance to the quality prediction.
- the most significant parameters can be any of those available by the network monitoring system, although the most common are the performance, the lost packet rate and the delay.
- the votes of the weights of phase v) are modeled using automatic learning regression models and the experience quality prediction platform comprises parameters selected from:
- Network parameters that contribute to the calculation of the user experience selected among content type, service result, user agent, sequence losses, assent losses, packet loss rate, percentage of packet loss, burst of loss of packages, maximum, minimum and average values of the performance, delay and variance of the delay and a combination thereof; Y,
- the machine learning algorithm of phase iii) of the method automatically identifies the network parameters that most affect QoE based on their relevance to quality prediction. This takes place in order to propose the necessary values to achieve a user-defined quality of experience. This procedure includes the following stages:
- the QoE algorithm indicates a certain number of parameters and the values that it should take (increase or decrease) to improve the user experience. This automatic procedure will depend on the training model, the values that the particular parameters take for each session, and the quality of the expected experience. In fact, the algorithm is able to identify the parameters that have most sensitively contributed to the perception by proposing a threshold for each session from which the quality of the experience would be desirable.
- the QoE prediction model that will be applied to the prediction platform is established.
- the second (stationary) phase uses it in a stationary manner, taking as input the network data, and generating an MOS value for each data network.
- the network data is obtained from the monitoring network, such as PSTN, PLMN, ATM, Frame Relay, SDH, PDH, TDM, SS7, GSM, GPRS, UMTS, HSDPA, HSUPA, LTE, SAE, WiMAX, Wi- Fi, IP, MPLS, NGN, IMS, IPTV, MobileTV, etc.
- the monitoring data is merged with the corresponding questionnaires to create a training set that serves as input to the QoE prediction models.
- a new record is created for each subjective data and each network data containing said register the most significant parameters that can contribute to the QoE.
- the method creates a training set where the result of the mixture of the network data with the questionnaires is stored.
- Each of the training sets is used as input for the machine learning algorithms to obtain the prediction models. These prediction models predict the subjective response values of the questionnaires based on the input data.
- prediction models can be applied depending on the scenario, such as decision trees, vector support machines, Bayesian networks, artificial neural networks, etc.
- a final prediction model is defined, which combines all the predictions into a single QoE MOS value. These predictions are combined using a weighted voting scheme, where the votes for the weights are modeled according to machine learning regression models. Different regression models can be constructed for the final prediction model based on the data from the training set of the last questionnaire questions such as linear regression, SMO regression, etc.
- the final QoE prediction model is implemented in the QoE prediction platform, which can also be part of any existing monitoring system. In this way, a value of MOS is calculated in real time for each new data of the data network In this stationary phase it is not necessary to use input data from the users.
- the prediction platform may include other parameters such as confidence prediction or network parameters that can contribute the most to obtaining the QoE.
- Figure 1. Shows a flow chart of the method to calculate the perception of user experience of the quality of the monitored services integrated in telecommunications operators, in a particular case.
- the input data of the network is the IP detail records (IPDR) acquired from the network through passive probes, generating an IPDR record 'at the exit for each user when using a service from the videostraming protocols involved, such as RTP, RTSP, RTCP ...
- IPDR IP detail records
- IPDRs (1) The most important parameters that affect the customer experience are: content, user identifier, server identifier, packet loss, delay, jitter, performance, initiation time and error.
- the detailed specifications and specific fields of these IPDRs (1) can be found in the recommendation "Quality of end-to-end monitoring service on converged IPTV platforms".
- the key component in the correlation algorithms (4) is the definition of unique attributes in both data sets (network data and questionnaire data) that allows their proper correlation.
- the correlation algorithm (4) is based on the following values:
- the prediction model (5) used in this exemplary embodiment is constructed from the machine learning algorithm C4.5 together with AdaBoost (adaptive amplifier), an algorithm that creates a set of classifiers.
- AdaBoost adaptive amplifier
- AdaBoost is a meta-algorithm and can be used in combination with many other machine learning algorithms to improve its performance.
- AdaBoost creates subsequent classifiers, emphasizing data that may have been previously misclassified.
- the model combines all the classifiers together in a single set with weighted vote.
- aggregation techniques based on the proximity of two nearby response values (for example, “excellent” and “very well, “are two of the possible responses with very similar subjective values)
- a greater accuracy of the model is obtained.
- the weights of the model are acquired by means of the vector support machine regression algorithm (SVM). In this way all the responses are combined with a regression model to give a single MOS QoE value (7).
- SVM vector support machine regression algorithm
- the preconfigured models for each issue about perceived quality are: ⁇
- Each model is based on data from subjective questionnaires using the Weka 3.7 ML platform.
- the prediction model is embedded in the QoE prediction platform, which is connected to the monitoring system.
- IPDR ' The output of the QoE prediction platform is an expanded set of the incoming IPDRs, called as IPDR ', which adds the following attributes for each IPDR':
- the application is intended to be highly configurable and adaptable to different functional configurations:
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Environmental & Geological Engineering (AREA)
- Telephonic Communication Services (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/ES2010/070324 WO2011141586A1 (fr) | 2010-05-14 | 2010-05-14 | Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications |
EP10851321.9A EP2571195A4 (fr) | 2010-05-14 | 2010-05-14 | Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications |
BR112012029162A BR112012029162A2 (pt) | 2010-05-14 | 2010-05-14 | método para calcular a percepção de experiência de usuário da qualidade dos serviços monitorados integrados em operadores de telecomunicações |
US13/697,891 US20130148525A1 (en) | 2010-05-14 | 2010-05-14 | Method for calculating perception of the user experience of the quality of monitored integrated telecommunications operator services |
ARP110101647A AR081041A1 (es) | 2010-05-14 | 2011-05-12 | Metodo para calcular la percepcion de experiencia de usuario de la calidad d elos servicios monitorizados integrados en operadores de telecomunicaciones |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/ES2010/070324 WO2011141586A1 (fr) | 2010-05-14 | 2010-05-14 | Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011141586A1 true WO2011141586A1 (fr) | 2011-11-17 |
Family
ID=44913979
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/ES2010/070324 WO2011141586A1 (fr) | 2010-05-14 | 2010-05-14 | Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications |
Country Status (5)
Country | Link |
---|---|
US (1) | US20130148525A1 (fr) |
EP (1) | EP2571195A4 (fr) |
AR (1) | AR081041A1 (fr) |
BR (1) | BR112012029162A2 (fr) |
WO (1) | WO2011141586A1 (fr) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013135734A1 (fr) * | 2012-03-12 | 2013-09-19 | Nokia Siemens Networks Oy | Prédiction et recommandations de cause profonde d'accès de qualité d'accès au service de problèmes d'expérience dans des réseaux de communication |
WO2014090308A1 (fr) * | 2012-12-13 | 2014-06-19 | Telefonaktiebolaget L M Ericsson (Publ) | Procédé et appareil pour évaluer l'expérience utilisateur |
WO2019101193A1 (fr) * | 2017-11-27 | 2019-05-31 | Telefonaktiebolaget Lm Ericsson (Publ) | Procédé et appareil permettant de prédire une qualité d'expérience relative à un service dans un réseau sans fil |
US10397067B2 (en) | 2013-11-20 | 2019-08-27 | International Business Machines Corporation | Determining quality of experience for communication sessions |
CN113115347A (zh) * | 2021-05-10 | 2021-07-13 | 游密科技(深圳)有限公司 | 面向应用共享服务的网络会议视觉质量自动化评估方法 |
CN113256022A (zh) * | 2021-06-16 | 2021-08-13 | 广东电网有限责任公司 | 一种台区用电负荷预测方法及系统 |
CN113364621A (zh) * | 2021-06-04 | 2021-09-07 | 浙江大学 | 服务网络环境下的服务质量预测方法 |
US11888919B2 (en) | 2013-11-20 | 2024-01-30 | International Business Machines Corporation | Determining quality of experience for communication sessions |
Families Citing this family (47)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9412123B2 (en) | 2003-07-01 | 2016-08-09 | The 41St Parameter, Inc. | Keystroke analysis |
US10999298B2 (en) | 2004-03-02 | 2021-05-04 | The 41St Parameter, Inc. | Method and system for identifying users and detecting fraud by use of the internet |
US11301585B2 (en) | 2005-12-16 | 2022-04-12 | The 41St Parameter, Inc. | Methods and apparatus for securely displaying digital images |
US8938671B2 (en) | 2005-12-16 | 2015-01-20 | The 41St Parameter, Inc. | Methods and apparatus for securely displaying digital images |
US8151327B2 (en) | 2006-03-31 | 2012-04-03 | The 41St Parameter, Inc. | Systems and methods for detection of session tampering and fraud prevention |
US9112850B1 (en) | 2009-03-25 | 2015-08-18 | The 41St Parameter, Inc. | Systems and methods of sharing information through a tag-based consortium |
US9634855B2 (en) | 2010-05-13 | 2017-04-25 | Alexander Poltorak | Electronic personal interactive device that determines topics of interest using a conversational agent |
KR101568620B1 (ko) | 2011-08-29 | 2015-11-11 | 엠파이어 테크놀로지 디벨롭먼트 엘엘씨 | 애플리케이션 단위로 단말기 상에서 추정된 qoe 들을 출력하는 방법 |
US10754913B2 (en) | 2011-11-15 | 2020-08-25 | Tapad, Inc. | System and method for analyzing user device information |
US8880689B2 (en) | 2011-12-22 | 2014-11-04 | Empire Technology Development Llc | Apparatus, mobile terminal, and method to estimate quality of experience of application |
US9633201B1 (en) | 2012-03-01 | 2017-04-25 | The 41St Parameter, Inc. | Methods and systems for fraud containment |
US9521551B2 (en) | 2012-03-22 | 2016-12-13 | The 41St Parameter, Inc. | Methods and systems for persistent cross-application mobile device identification |
US9275334B2 (en) * | 2012-04-06 | 2016-03-01 | Applied Materials, Inc. | Increasing signal to noise ratio for creation of generalized and robust prediction models |
US9438883B2 (en) | 2012-04-09 | 2016-09-06 | Intel Corporation | Quality of experience reporting for combined unicast-multicast/broadcast streaming of media content |
WO2014022813A1 (fr) | 2012-08-02 | 2014-02-06 | The 41St Parameter, Inc. | Systèmes et procédés d'accès à des enregistrements via des localisateurs de dérivé |
WO2014078569A1 (fr) | 2012-11-14 | 2014-05-22 | The 41St Parameter, Inc. | Systèmes et procédés d'identification globale |
US20140229210A1 (en) * | 2013-02-14 | 2014-08-14 | Futurewei Technologies, Inc. | System and Method for Network Resource Allocation Considering User Experience, Satisfaction and Operator Interest |
GB2512300A (en) * | 2013-03-25 | 2014-10-01 | Celkee Oy | Electronic arrangement and related method for dynamic resource management |
FI125573B (en) * | 2013-08-27 | 2015-11-30 | Elisa Oyj | Adaptive service management that takes into account disruption |
US10902327B1 (en) | 2013-08-30 | 2021-01-26 | The 41St Parameter, Inc. | System and method for device identification and uniqueness |
GB201320216D0 (en) * | 2013-11-15 | 2014-01-01 | Microsoft Corp | Predicting call quality |
WO2015073470A1 (fr) * | 2013-11-15 | 2015-05-21 | Microsoft Technology Licensing, Llc | Prédiction de qualité d'appel |
US20150373565A1 (en) * | 2014-06-20 | 2015-12-24 | Samsung Electronics Co., Ltd. | Quality of experience within a context-aware computing environment |
ES2838399T3 (es) * | 2014-09-17 | 2021-07-01 | Deutsche Telekom Ag | Método y aparato para calcular la calidad percibida de un servicio o sistema de telecomunicaciones audiovisual o de audio de múltiples participantes |
US10091312B1 (en) | 2014-10-14 | 2018-10-02 | The 41St Parameter, Inc. | Data structures for intelligently resolving deterministic and probabilistic device identifiers to device profiles and/or groups |
US9641681B2 (en) * | 2015-04-27 | 2017-05-02 | TalkIQ, Inc. | Methods and systems for determining conversation quality |
EP3182647A1 (fr) | 2015-12-18 | 2017-06-21 | Telefonica Digital España, S.L.U. | Procédé pour effectuer une estimation de qualité de réseau hors couverture et ses produits de programmes informatiques |
US10454989B2 (en) * | 2016-02-19 | 2019-10-22 | Verizon Patent And Licensing Inc. | Application quality of experience evaluator for enhancing subjective quality of experience |
WO2017152932A1 (fr) * | 2016-03-07 | 2017-09-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Procédé et nœud de notation pour l'estimation de la qualité de confort d'un utilisateur pour un service fourni |
EP3223279B1 (fr) * | 2016-03-21 | 2019-01-09 | Nxp B.V. | Circuit de traitement de signal vocal |
US10154138B2 (en) * | 2016-07-29 | 2018-12-11 | Genesys Telecommunications Laboratories, Inc. | System and method for optimizing physical placement of contact center agents on a contact center floor |
US10158757B2 (en) | 2016-07-29 | 2018-12-18 | Genesys Telecommunications Laboratories, Inc. | System and method for optimizing contact center resource groups |
US9792908B1 (en) * | 2016-10-28 | 2017-10-17 | International Business Machines Corporation | Analyzing speech delivery |
US10791026B2 (en) * | 2016-11-10 | 2020-09-29 | Ciena Corporation | Systems and methods for adaptive over-the-top content quality of experience optimization |
US10862771B2 (en) | 2016-11-10 | 2020-12-08 | Ciena Corporation | Adaptive systems and methods enhancing service quality of experience |
US10798387B2 (en) | 2016-12-12 | 2020-10-06 | Netflix, Inc. | Source-consistent techniques for predicting absolute perceptual video quality |
CN107087160A (zh) * | 2017-04-28 | 2017-08-22 | 南京邮电大学 | 一种基于BP‑Adaboost神经网络的用户体验质量的预测方法 |
WO2019129803A1 (fr) * | 2017-12-28 | 2019-07-04 | Telecom Italia S.P.A. | Collecte de données pour évaluer la qualité d'expérience d'un service sur un réseau de communications |
WO2019177481A1 (fr) * | 2018-03-12 | 2019-09-19 | Ringcentral, Inc., (A Delaware Corporation) | Système et procédé d'évaluation de la qualité d'une session de communication |
FR3095100B1 (fr) * | 2019-04-15 | 2021-09-03 | Continental Automotive | Procédé de prédiction d’une qualité de signal et/ou de service et dispositif associé |
CA3140213A1 (fr) * | 2019-05-16 | 2020-11-19 | Canopus Networks Pty Ltd | Procede et appareil pour l'estimation d'une qualite d'experience en temps reel |
US11606262B2 (en) * | 2019-11-08 | 2023-03-14 | International Business Machines Corporation | Management of a computing system with multiple domains |
CN111401637B (zh) * | 2020-03-16 | 2023-06-16 | 湖南大学 | 融合用户行为和表情数据的用户体验质量预测方法 |
CN113839906B (zh) * | 2020-06-08 | 2022-12-30 | 华为技术有限公司 | 音视频流质量的确定方法、装置、设备及可读存储介质 |
EP4189932A1 (fr) * | 2020-08-03 | 2023-06-07 | Telefonaktiebolaget LM Ericsson (publ) | Corrélation de données de réseau avec une rétroaction d'application instantanée pour une gestion d'expérience client basée sur ml |
CN115065606B (zh) * | 2022-05-31 | 2023-10-27 | 中移(杭州)信息技术有限公司 | 家宽质差分析方法、装置、设备及存储介质 |
CN115314407A (zh) * | 2022-08-03 | 2022-11-08 | 东南大学 | 一种基于网络流量的网络游戏QoE检测方法 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070004399A1 (en) * | 2005-06-29 | 2007-01-04 | Nokia Corporation | Quality assessment for telecommunications network |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8081565B2 (en) * | 2005-04-21 | 2011-12-20 | Avaya Inc. | Method and apparatus for adaptive control of system parameters for admission control |
DE602005007620D1 (de) * | 2005-12-14 | 2008-07-31 | Ntt Docomo Inc | Vorrichtung und Verfahren zur Bestimmung der Übertragungspolitik für mehrere und verschiedenartige Anwendungen |
US20070271590A1 (en) * | 2006-05-10 | 2007-11-22 | Clarestow Corporation | Method and system for detecting of errors within streaming audio/video data |
US8656284B2 (en) * | 2009-04-17 | 2014-02-18 | Empirix Inc. | Method for determining a quality of user experience while performing activities in IP networks |
-
2010
- 2010-05-14 WO PCT/ES2010/070324 patent/WO2011141586A1/fr active Application Filing
- 2010-05-14 BR BR112012029162A patent/BR112012029162A2/pt not_active IP Right Cessation
- 2010-05-14 US US13/697,891 patent/US20130148525A1/en not_active Abandoned
- 2010-05-14 EP EP10851321.9A patent/EP2571195A4/fr not_active Withdrawn
-
2011
- 2011-05-12 AR ARP110101647A patent/AR081041A1/es unknown
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070004399A1 (en) * | 2005-06-29 | 2007-01-04 | Nokia Corporation | Quality assessment for telecommunications network |
Non-Patent Citations (6)
Title |
---|
"Decision tree compared to regression and neural networks", 17 June 2008 (2008-06-17), XP008167248, Retrieved from the Internet <URL:http://www.dtreg.com/othermethods.htm> [retrieved on 20100203] * |
"Methods for subjective determination of transmission quality", ITU-T RECOMMENDATION, pages 800 |
"Quality of Experience", 17 September 2009 (2009-09-17), XP008167247, Retrieved from the Internet <URL:http://en.wikipedia.org/w/index.php?title=Quality_of_experience&oldid=314511091> [retrieved on 20100203] * |
"Subjective evaluation of conversational quality", ITU-T RECOMMENDATION, 2007, pages 805 |
KETYKO ET AL.: "Performing QoE-measurements in an actual 3G network", 2010 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB 2010), 26 March 2010 (2010-03-26), PISCATAWAY, NJ, USA., XP031675518 * |
See also references of EP2571195A4 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013135734A1 (fr) * | 2012-03-12 | 2013-09-19 | Nokia Siemens Networks Oy | Prédiction et recommandations de cause profonde d'accès de qualité d'accès au service de problèmes d'expérience dans des réseaux de communication |
KR20140145151A (ko) * | 2012-03-12 | 2014-12-22 | 노키아 솔루션스 앤드 네트웍스 오와이 | 통신 네트워크들에서 서비스 액세스 경험 품질 이슈들의 예측 및 근본 원인 추천들 |
US9152925B2 (en) | 2012-03-12 | 2015-10-06 | Nokia Solutions And Networks Oy | Method and system for prediction and root cause recommendations of service access quality of experience issues in communication networks |
KR101676743B1 (ko) | 2012-03-12 | 2016-11-16 | 노키아 솔루션스 앤드 네트웍스 오와이 | 통신 네트워크들에서 서비스 액세스 경험 품질 이슈들의 예측 및 근본 원인 추천들 |
WO2014090308A1 (fr) * | 2012-12-13 | 2014-06-19 | Telefonaktiebolaget L M Ericsson (Publ) | Procédé et appareil pour évaluer l'expérience utilisateur |
US10397067B2 (en) | 2013-11-20 | 2019-08-27 | International Business Machines Corporation | Determining quality of experience for communication sessions |
US11888919B2 (en) | 2013-11-20 | 2024-01-30 | International Business Machines Corporation | Determining quality of experience for communication sessions |
WO2019101193A1 (fr) * | 2017-11-27 | 2019-05-31 | Telefonaktiebolaget Lm Ericsson (Publ) | Procédé et appareil permettant de prédire une qualité d'expérience relative à un service dans un réseau sans fil |
CN113115347A (zh) * | 2021-05-10 | 2021-07-13 | 游密科技(深圳)有限公司 | 面向应用共享服务的网络会议视觉质量自动化评估方法 |
CN113364621A (zh) * | 2021-06-04 | 2021-09-07 | 浙江大学 | 服务网络环境下的服务质量预测方法 |
CN113364621B (zh) * | 2021-06-04 | 2022-07-26 | 浙江大学 | 服务网络环境下的服务质量预测方法 |
CN113256022A (zh) * | 2021-06-16 | 2021-08-13 | 广东电网有限责任公司 | 一种台区用电负荷预测方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
EP2571195A4 (fr) | 2014-08-13 |
AR081041A1 (es) | 2012-05-30 |
EP2571195A1 (fr) | 2013-03-20 |
US20130148525A1 (en) | 2013-06-13 |
BR112012029162A2 (pt) | 2017-02-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2011141586A1 (fr) | Procédé pour calculer la perception d'expérience d'utilisateur de la qualité des services surveillés intégrés chez des opérateurs de télécommunications | |
Rodríguez et al. | Video quality assessment in video streaming services considering user preference for video content | |
US11770569B2 (en) | Providing risk based subscriber enhancements | |
Batteram et al. | Delivering quality of experience in multimedia networks | |
Liotou et al. | A roadmap on QoE metrics and models | |
Kim et al. | QoE assessment model for multimedia streaming services using QoS parameters | |
Baraković et al. | QoE dimensions and QoE measurement of NGN services | |
Wang et al. | VQM-based QoS/QoE mapping for streaming video | |
Reichl | From charging for quality of service to charging for quality of experience | |
Aguiar et al. | Video quality estimator for wireless mesh networks | |
Ghalut et al. | Non-intrusive method for video quality prediction over lte using random neural networks (rnn) | |
Carofiglio et al. | Characterizing the relationship between application QoE and network QoS for real-time services | |
US11522939B2 (en) | Over-the-top media service testing and QoE issues isolation | |
Kimura et al. | QUVE: QoE maximizing framework for video-streaming | |
Rodríguez et al. | A billing system model for voice call service in cellular networks based on voice quality | |
US11399202B2 (en) | Analytics in video/audio content distribution networks | |
García-Pineda et al. | Adaptive SDN-based architecture using QoE metrics in live video streaming on Cloud Mobile Media | |
Dai | A survey of quality of experience | |
Jian et al. | Customer experience oriented service quality management | |
Diallo | Quality of experience and video services adaptation | |
Msakni et al. | Provisioning QoE over converged networks: Issues and challenges | |
Tran et al. | Qoe model driven for network services | |
Kowalik et al. | Telecom Operator’s Approach to QoE | |
Diallo et al. | A hybrid contextual user perception model for streamed video quality assessment | |
Hsu et al. | Web-based QoE measurement framework |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10851321 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010851321 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13697891 Country of ref document: US |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112012029162 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112012029162 Country of ref document: BR Kind code of ref document: A2 Effective date: 20121114 |